ABSTRACT: In this study, an artificial neural networks (ANN) model as an artificial intelligence (AI) technique is proposed to determine the formation pore pressure from data of two critical drilling parameters named mechanical specific energy and drilling efficiency. These parameters (MSE and DE) which are closely correlated to differential pressure during drilling were chosen as a result of a literature review of proposed methods of pore pressure estimation. Collected data of a three wellbores drilled in an Iranian sandstone formation were used for the purpose of this research, and pore pressure estimated using this model was in a good agreement with estimates from previously published models including the one derived from conventional sonic logs data. The proposed model results were analyzed, and proved that artificial neural networks are capable to provide reliable independent predictions of pore pressure, and this smart model can be hired to analyze data for pre-drilling prediction models construction and post-well prediction models optimization.
Nowadays, many drilling operations are not being performed with optimum efficiency and management of costs, time and quality. Thus, drilling optimization has become an important and critical challenge for drilling operators in the petroleum industry as there are a lot of variables for consideration in drilling systems optimization. Real-time analysis of drilling parameters’ data is a way to understand drilling mechanics and efficiency. (Amadi and Iyalla, 2012)
Estimates of Formation Pore Pressure before and while drilling, and recognizing deviations from the expected pressure are important inputs for well planning and operational decision making. The effect of Differential Pressure (wellbore pressure minus pore pressure) on drilling responses has long been recognized, and drilling efficiency (DE) and mechanical specific energy (MSE) are chosen as parameters highly correlated to the differential pressure. (Majidi et al. 2016)
Logs and drilling mechanics based estimation methods are independent models of pore pressure estimation when suitable data are available. However, the advantage of drilling mechanics method is that it can provide pressure while drilling in real-time at the bit, not behind the bit, and the error would be diminished.